Purecode Software

Role : AI Research Engineer - AI Pair Programming About Us : We are developing a cutting-edge AI pair programming extension for VS Code, aimed at revolutionising the way developers write code. Our mission is to enhance developer productivity and code quality through advanced AI assistance. We're seeking an experienced AI Research Engineer to join our innovative team at PureCode AI and help push the boundaries of AI in software development. Position Overview : We are looking for an AI Research Engineer with a strong background in Large Language Models (LLMs) and their applications in code generation and understanding. The ideal candidate will contribute to our research efforts in contextual retrievals, rerankers, and vector databases, with a focus on optimising developer workflows. Key Responsibilities : - Conduct advanced research in AI and machine learning, specifically focusing on LLMs for code generation and comprehension - Implement or optimise state-of-the-art AI models to enhance our AI pair programming capabilities - Develop and refine algorithms for contextual code retrieval, reranking, and efficient use of vector databases - Collaborate with the development team to integrate research findings into our VS Code extension - Contribute to the improvement of developer workflow optimisation through AI-assisted coding - Evaluate and fine-tune models to ensure high-quality code suggestions and analysis - Stay abreast of the latest advancements in AI research and propose innovative applications for our product Qualifications : - Bachelor's or Master's degree in Computer Science, Artificial Intelligence, or a related field - Minimum of 3 years of experience in AI engineering and research, with a focus on NLP and LLMs - Strong background in machine learning, deep learning, and natural language processing - Expertise in implementing and deploying AI models for code analysis and generation - Experience with contextual retrieval systems, rerankers, and vector databases - Proficiency in Python and familiarity with machine learning frameworks such as PyTorch or TensorFlow - Solid understanding of API development practices and tools, particularly in the context of Generative AI. - Familiarity with VS Code extension development is a plus Required Skills : - Strong problem-solving skills and ability to translate research into practical applications - Excellent programming skills and ability to write clean, efficient code - Good understanding of software engineering principles and best practices - Ability to work effectively in a collaborative team environment - Strong communication skills to explain complex AI concepts to both technical and non-technical stakeholders - Self-motivated with the ability to work independently on research projects Preferred Experience : - Previous work on AI-assisted coding tools or IDE plugins - Contributions to open-source AI or developer tool projects - Experience with large-scale machine learning model deployment and optimisation - Familiarity with MLOps practices and tools What We Offer : - Opportunity to work on cutting-edge AI technology that directly impacts developers worldwide - Collaborative and innovative work environment - Competitive salary and benefits package - Professional development opportunities and support for attending relevant conferences - Chance to publish and present research findings in academic and industry forums Location- Delhi NCR, Bangalore, Chennai, Pune, Kolkata, Ahmedabad, Mumbai, Hyderabad

Conduct advanced research in AI and machine learning, specifically focusing on LLMs for Expertise in Linux System Admin and Bash Scripting Work with version control systems, particularly Git and GitHub, to ensure proper versioning, branching, and merging of code Experience in Build and Deployment of multi environments application. Utilise your expertise in cloud platforms such as Azure, OCI, and AWS to architect and maintain scalable Infrastructure Experience with Maintaining security of the application on cloud (Azure/OCI/AWS) Understanding network topologies and common network protocols and services (DNS, HTTP(S), SSH, FTP, SMTP). Hands on Experience in one of the tools for Infrastructure as a code - like Terraform, ARM templates . Hands on Experience with setting up and monitoring Databases(SQL/NoSQL) on cloud (Azure/OCI/AWS) Experience in Implementation of CI-CD using Github Actions, Jenkins, Azure Pipelines Proficiency in container frameworks like Docker and Kubernetes An ability to conveniently deploy monitoring and logging infrastructure using tools like Kubernetes Collaborate with cross-functional teams to understand software requirements and design effective DevOps strategies. Excellent proficiency in problem solving and troubleshooting technical issues. Excellent interpersonal and communication skills. Ability to handle multiple competing priorities in a fast-paced environment. Motivation to drive tasks to completion and take ownership of projects.

1. Distributed API design and tracing, further in-depth discussion based on candidate's answer to know depth of his knowledge 2. Javascript/NodeJS internal working, concepts like worker threads, event propagation 3. Typescript questions : what are generics, how types are different from interfaces? 4. What type of AI applications you've worked on ? How does Agentic RAG, knowledge base works? 5. Must have excellent problem-solving Skills 6. Experience with low level design and High level design 7. Design a system for Authentication and Authorization server that has following capabilities to it's client(frontend) a. Considering we have two product offering 1. Web platform 2. vs code extension , User should be able to have active session in both at same time. (user can have multiple active session from multiple browsers but with upper limit as 10 sessions combined) b. User should be able to remove other sessions from any active session c. Active or inactive , session history must be preserved for usage and tracing purpose. d. If user uses /get_completion API route then upon successful call an usage should be updated and do not allow the api call if user does not have any usage left. (consider that user has a subscription that has certain limit for usage such as 50 calls.) e. Design detailed database diagram and system flow diagram for the requirements mentioned above

About PureCode AI : PureCode is a front-end developer tool where engineers can use text to describe and generate or customize software user interfaces - (and soon entire projects). Our goal is to build a must use developer tool for front-end engineers to build web software 100x faster! We are headquartered in Austin, TX, USA with engineering offices in Hyderabad, India. This position is for exclusively in office work at our Q City Office in Hyderabad. Responsibilities : - Designing and implementing advanced state-of-the-art AI models, specializing in LLMs, VLMs and MLLMs. - Develop ML models, fine tune and work with stakeholders in finalising champion models. Perform scientific evaluation of NLP/LLM models, come up with new techniques for model validation, evaluation, trust and safety. - Understand how customer business needs are mapped to AI/ML problem and solution involving Algorithms/Models. - Support the process of Translating business problems into ML problems and create ML solutions to produce desired customer business outcomes. - Develop MLOps (Machine Learning Operations) workflows for data preparation, deployment, monitoring and retraining. Create and own cloud native API to deploy ML Models - Craft data warehousing strategy alongwith instrumenting ETL pipelines for maintaining quality data to be used for Model Training. - Design and implement A/B experiments - user segmentation, user classification, and tooling to support A/B experiments. Qualifications : - 3+ years of working experience developing, deploying, tracking and orchestrating scalable ML/AI solutions. - Familiarity with cloud platforms and services such as AWS, Azure, or GCP for deploying and scaling AI solutions. - Knowledge of basic ML stack - Pytorch, tensorflow, sklearn, numpy, pandas, etc. - Familiarity with experiment tracking tools like Weights & Biases, TensorBoard, or ClearML. - Hands on experience with MLOps tools like Mlflow, CometML, Docker, etc. - Hand on experience with workflow orchestration tools like Airflow, Prefect, or Databricks, etc. - Knowledge of API frameworks Django, Flask etc. - Knowledge of web development tools is a plus. - Knowledge of LLMops, langchain framework is a plus

Position Overview : We are seeking an experienced and forward-thinking Senior Node.js Engineer to play a pivotal role in architecting and developing the backend infrastructure that powers our AI-driven product suite. This position offers a unique opportunity to work at the intersection of Node.js development and artificial intelligence, contributing directly to products that are reshaping the software development landscape. Responsibilities : - Develop high-quality, well-tested, secure, scalable, and maintainable Node.js applications - Design and implement robust REST and GraphQL APIs - Create resilient backend services adaptable to changing business needs - Research and integrate new technologies to improve efficiency and enhance user experience - Collaborate with US-based product and sales teams to implement customer-requested features - Perform code reviews and mentor junior developers Qualifications : - 3+ years of experience as a backend developer, with a strong focus on Node.js - Extensive experience with Node.js and related frameworks (e.g., Express.js, Fastify) - Expertise in building and maintaining robust REST and GraphQL APIs - Proficiency with Next.js - Strong knowledge of MongoDB and other NoSQL databases - Experience with SQL databases (PostgreSQL, MySQL) - Proficiency with caching solutions such as Redis - Familiarity with WebSocket technologies for real-time applications - Solid understanding of software design principles and patterns - Proficiency with Git for version control - Experience with containerization and microservices architecture (preferred)

Responsibilities: Help improve our website, blog, and landing pages for better user experience, SEO performance, and higher conversions. Conduct basic keyword research, optimize on-page SEO elements, and help ensure content is search-friendly. Assist in managing marketing activities, including YouTube marketing, SEO, and email campaigns. Collaborate with the development team to ensure our site is user-friendly, visually appealing, optimized for search engines, and free of bugs. Run tests and suggest improvements to enhance the customer journey and support lead-generation efforts. Contribute to updating website content and design elements to maintain consistency, quality, and SEO best practices. Qualifications: 6+ months of experience in SEO or digital marketing, with a basic understanding of SEO principles like keyword research, on-page optimization, and content structuring. Familiarity with CRO techniques and an interest in learning how to improve conversion rates. Experience with WordPress, Webflow, or other no-code tools is a plus. Good communication skills and attention to detail. Ability to manage tasks and stay organized in a fast-paced environment. Analytical mindset, comfortable with data, and a willingness to learn and grow in SEO and CRO.

LLM & Prompt Engineer About PureCode AI : PureCode is a front-end developer tool where engineers can use text to describe and generate or customize software user interfaces - (and soon entire projects). Our goal is tobuild a must use developer tool for front-end engineers to build web software 100x faster! We are headquartered in Austin, TX, USA with engineering offices in Bangalore, India. This position is for exclusively in office work in Bangalore. Please visit our site to understand our product before applying https://purecode.ai/ Responsibilities : - Develop and optimize prompts for AI systems to assist developers in generating high-quality code, improving documentation, and automating tasks. - Designing, Developing and Refining prompts to enhance the quality and relevance of generated response. - Monitor and analyze prompt's performance to identify areas of improvements. - Understand user behavior and requirements and develop accordingly. - Stay proactive in identifying opportunities for innovation and improvement in our AI systems. - Stay up to date with advancements in AI, NLP, and prompt engineering, and apply this knowledge to improve our products and processes. - Conduct experiments to test and evaluate the effectiveness of different prompts in producing optimal results for end users. Qualifications : - Knowledge of LLM parameters and configuring these parameters to get different results for prompt. - Understanding of all prompt elements and experience in modifying those elements to get better results. - Experience with existing prompting techniques. - Experience with using suitable prompts for various applications (e.g. Generating code, Generating data, etc.). - Experience with RAG and handling hierarchical data (e.g. Codebase) for RAG. - Knowledge of capabilities of various LLMs and how can we use different prompts efficiently to improve the capacity of LLMs. - Knowledge of scaling, agents, efficiency, hallucination, prompt injection, etc. - Understanding of Graph databases and Tabular databases and utilization of prompts to make LLM interact with these databases. - Knowledge of latest research on prompt engineering for LLMs.

Conduct advanced research in AI and machine learning, specifically focusing on LLMs for code generation and comprehension Implement or optimise state-of-the-art AI models to enhance our AI pair programming capabilities Develop and refine algorithms for contextual code retrieval, reranking, and efficient use of vector databases Collaborate with the development team to integrate research findings into our VS Code extension Contribute to the improvement of developer workflow optimisation through AI-assisted coding Evaluate and fine-tune models to ensure high-quality code suggestions and analysis Stay abreast of the latest advancements in AI research and propose innovative applications for our product

Responsibilities Develop and optimize prompts for AI systems to assist developers in generating high-quality code, improving documentation, and automating tasks. Designing, Developing and Refining prompts to enhance the quality and relevance of generated response. Monitor and analyze prompts performance to identify areas of improvements. Understand user behavior and requirements and develop accordingly. Stay proactive in identifying opportunities for innovation and improvement in our AI systems. Stay up to date with advancements in AI, NLP, and prompt engineering, and apply this knowledge to improve our products and processes. Conduct experiments to test and evaluate the effectiveness of different prompts in producing optimal results for end users. Qualifications Knowledge of LLM parameters and configuring these parameters to get different results for prompt. Understanding of all prompt elements and experience in modifying those elements to get better results. Experience with existing prompting techniques. Experience with using suitable prompts for various applications (e.g. Generating code, Generating data, etc.). Experience with RAG and handling hierarchical data (e.g. Codebase) for RAG. Knowledge of capabilities of various LLMs and how can we use different prompts efficiently to improve the capacity of LLMs. Knowledge of scaling, agents, efficiency, hallucination, prompt injection, etc. Understanding of Graph databases and Tabular databases and utilization of prompts to make LLM interact with these databases. Knowledge of latest research on prompt engineering for LLMs.

Designing and implementing advanced state-of-the-art AI architectures, specializing in LLMs, SLMs, VLMs and MLLMs. Develop Gen AI workflows, fine tune and work with stakeholders. Perform scientific evaluation of NLP/LLM models, come up with new techniques for model validation, evaluation, trust and safety. Understand user behavior and requirements and develop accordingly. Write Generative AI pipelines to give contextual awareness of structured and unstructured data to LLMs. Develop MLOps (Machine Learning Operations) workflows for data preparation, deployment, monitoring and retraining. Create and own cloud native API to deploy ML models. Craft data warehousing strategy along with instrumenting ETL pipelines for maintaining quality data to be used for Model Training. Design and implement A/B experiments user segmentation, user classification, and tooling to support A/B experiments. Research and apply state-of-the-art techniques in Deep Learning and Generative AI Domain. Build and enhance NLP pipelines for hierarchical data.

Responsibilities - Ship high-quality, well-tested, secure, scalable, extensible, and maintainable code as well as perform code review. Apply design principles and patterns in creating enterprise-level solutions, as needed. Design products, services, and systems that are resilient to the iteration and change required by the needs of the business. Research new technologies and development methodologies to drive efficiency and improve customer experience. Coordination with the US led product and sales team to strategize and carry out the development of customer features and functionality requests. Qualifications - 3+ years of experience as a Full stack developer. Extensive experience working with NodeJS platforms & MongoDB. Expertise in building robust REST and GraphQL APIs Experience working with ReactJs Hooks. Hands-on experience with frameworks like ExpressJS and Fastify. Proficiency with SQL/NoSQL databases like PostgreSQL, MySQL and Redis. Hands-on experience in working with React-related libraries like Redux, MaterialUI and frameworks like NextJS. Strong knowledge of source code management systems like git & knowledge of WebSocket technologies.